Flood susceptibility mapping using a novel integration of multi-temporal sentinel-1 data and eXtreme deep learning model

• DOI: 10.1016/j.gsf.2024.101780
• Publication Date: 2024-01-09T16:51:56Z
• Authors: Rami Al-Ruzouq; Abdallah Shanableh; Ratiranjan Jena; Mohammed Barakat ...; Nezar Atalla Hamm...; Fouad Lamghari
• Keywords: Flash flood

Flash floods (FFs) are amongst the most devastating hazards in arid regions response to climate change and can cause loss of agricultural land, human lives infrastructure. One major challenges is high-intensity rainfall events affecting low-lying areas that vulnerable FF. Several works this field have been conducted using ensemble machine learning models geohydrological models. However, current advancement eXtreme deep learning, which named factorisation (xDeepFM), for FF susceptibility mapping (FSM) lacking literature. The study introduces a new model employs previously unapplied approach enhance FSM capturing severity floods. proposed has three main objectives: (i) During- after-flood effects assessed through flood detection techniques Sentinel-1 data. (ii) Flood inventory updated remote sensing-based methods. derived implemented next step. (iii) An map generated an xDeepFM model. Therefore, aims apply estimate susceptible 13 factors emirates Fujairah, UAE. performance metrics show recall 0.9488), F1-score 0.9107), precision (0.8756) overall accuracy 90.41%. applied compared with traditional models, specifically neural network (78%), support vector (85.4%) random forest (88.75%). Random achieves high accuracy, due its strong depends on contribution, dataset size quality, available computational resources. Comparatively, efficiently complicated prediction problems having non-collinearity huge datasets. obtained denotes narrow basins, lowland coastal riverbank up 5 km (Fujairah) highly prone FF, whilst alluvial plains Al Dhaid hilly Fujairah low probability. city bounded by high-rise steep hills Gulf Oman, elevate water levels during heavy rainfall. Four synchronised influencing factors, namely, rainfall, elevation, drainage density, distance from geomorphology, account nearly 50% total contributing very susceptibility. This offers platform planners decision makers take timely actions potential mitigating